JMH使用说明「建议收藏」

mvn archetype:generate \
          -DinteractiveMode=false \
          -DarchetypeGroupId=org.openjdk.jmh \
          -DarchetypeArtifactId=jmh-java-benchmark-archetype \
          -DgroupId=co.speedar.infra \
          -DartifactId=jmh-test \
          -Dversion=1.0

    <dependency>
        <groupId>org.openjdk.jmh</groupId>
        <artifactId>jmh-core</artifactId>
        <version>0.7.1</version>
    </dependency>
    <dependency>
        <groupId>org.openjdk.jmh</groupId>
        <artifactId>jmh-generator-annprocess</artifactId>
        <version>0.7.1</version>
        <scope>provided</scope>
    </dependency>
...
    <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-shade-plugin</artifactId>
        <version>2.0</version>
        <executions>
            <execution>
                <phase>package</phase>
                <goals>
                    <goal>shade</goal>
                </goals>
                <configuration>
                    <finalName>microbenchmarks</finalName>
                    <transformers>
                        <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                            <mainClass>org.openjdk.jmh.Main</mainClass>
                        </transformer>
                    </transformers>
                </configuration>
            </execution>
        </executions>
    </plugin>

package co.speedar.infra.test;
import java.util.concurrent.TimeUnit;
import org.openjdk.jmh.annotations.Benchmark;
import org.openjdk.jmh.annotations.BenchmarkMode;
import org.openjdk.jmh.annotations.Mode;
import org.openjdk.jmh.annotations.OutputTimeUnit;
import org.openjdk.jmh.annotations.Scope;
import org.openjdk.jmh.annotations.State;
import org.openjdk.jmh.runner.Runner;
import org.openjdk.jmh.runner.RunnerException;
import org.openjdk.jmh.runner.options.Options;
import org.openjdk.jmh.runner.options.OptionsBuilder;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@BenchmarkMode(Mode.AverageTime) // 测试方法平均执行时间
@OutputTimeUnit(TimeUnit.MICROSECONDS) // 输出结果的时间粒度为微秒
@State(Scope.Thread) // 每个测试线程一个实例
public class FirstBenchMark { 
   
    private static Logger log = LoggerFactory.getLogger(FirstBenchMark.class);
    @Benchmark
    public String stringConcat() {
        String a = "a";
        String b = "b";
        String c = "c";
        String s = a + b + c;
        log.debug(s);
        return s;
    }
    public static void main(String[] args) throws RunnerException {
        // 使用一个单独进程执行测试，执行5遍warmup，然后执行5遍测试
        Options opt = new OptionsBuilder().include(FirstBenchMark.class.getSimpleName()).forks(1).warmupIterations(5)
                .measurementIterations(5).build();
        new Runner(opt).run();
    }
}

# JMH 1.14.1 (released 525 days ago, please consider updating!)
# VM version: JDK 1.8.0_91, VM 25.91-b14
# VM invoker: /Library/Java/JavaVirtualMachines/jdk1.8.0_91.jdk/Contents/Home/jre/bin/java
# VM options: -Dfile.encoding=UTF-8
# Warmup: 5 iterations, 1 s each
# Measurement: 5 iterations, 1 s each
# Timeout: 10 min per iteration
# Threads: 1 thread, will synchronize iterations
# Benchmark mode: Average time, time/op
# Benchmark: co.speedar.infra.test.FirstBenchMark.stringConcat
# Run progress: 0.00% complete, ETA 00:00:10
# Fork: 1 of 1
# Warmup Iteration 1: 0.009 us/op
# Warmup Iteration 2: 0.011 us/op
# Warmup Iteration 3: 0.007 us/op
# Warmup Iteration 4: 0.006 us/op
# Warmup Iteration 5: 0.006 us/op
Iteration   1: 0.006 us/op
Iteration   2: 0.005 us/op
Iteration   3: 0.005 us/op
Iteration   4: 0.006 us/op
Iteration   5: 0.006 us/op

Result "stringConcat":
  0.006 ±(99.9%) 0.001 us/op [Average]
  (min, avg, max) = (0.005, 0.006, 0.006), stdev = 0.001
  CI (99.9%): [0.005, 0.006] (assumes normal distribution)

# Run complete. Total time: 00:00:10
Benchmark                    Mode  Cnt  Score    Error  Units
FirstBenchMark.stringConcat  avgt    5  0.006 ±  0.001  us/op

public class JMHSample_02_BenchmarkModes { 
   
    @Benchmark
    @BenchmarkMode(Mode.Throughput)
    @OutputTimeUnit(TimeUnit.SECONDS)
    public void measureThroughput() throws InterruptedException {
        TimeUnit.MILLISECONDS.sleep(100);
    }
    /* * Mode.AverageTime measures the average execution time, and it does it * in the way similar to Mode.Throughput. * * Some might say it is the reciprocal throughput, and it really is. * There are workloads where measuring times is more convenient though. */
    @Benchmark
    @BenchmarkMode(Mode.AverageTime)
    @OutputTimeUnit(TimeUnit.MICROSECONDS)
    public void measureAvgTime() throws InterruptedException {
        TimeUnit.MILLISECONDS.sleep(100);
    }
    /* * Mode.SampleTime samples the execution time. With this mode, we are * still running the method in a time-bound iteration, but instead of * measuring the total time, we measure the time spent in *some* of * the benchmark method calls. * * This allows us to infer the distributions, percentiles, etc. * * JMH also tries to auto-adjust sampling frequency: if the method * is long enough, you will end up capturing all the samples. */
    @Benchmark
    @BenchmarkMode(Mode.SampleTime)
    @OutputTimeUnit(TimeUnit.MICROSECONDS)
    public void measureSamples() throws InterruptedException {
        TimeUnit.MILLISECONDS.sleep(100);
    }
    /* * Mode.SingleShotTime measures the single method invocation time. As the Javadoc * suggests, we do only the single benchmark method invocation. The iteration * time is meaningless in this mode: as soon as benchmark method stops, the * iteration is over. * * This mode is useful to do cold startup tests, when you specifically * do not want to call the benchmark method continuously. */
    @Benchmark
    @BenchmarkMode(Mode.SingleShotTime)
    @OutputTimeUnit(TimeUnit.MICROSECONDS)
    public void measureSingleShot() throws InterruptedException {
        TimeUnit.MILLISECONDS.sleep(100);
    }
    /* * We can also ask for multiple benchmark modes at once. All the tests * above can be replaced with just a single test like this: */
    @Benchmark
    @BenchmarkMode({Mode.Throughput, Mode.AverageTime, Mode.SampleTime, Mode.SingleShotTime})
    @OutputTimeUnit(TimeUnit.MICROSECONDS)
    public void measureMultiple() throws InterruptedException {
        TimeUnit.MILLISECONDS.sleep(100);
    }
    /* * Or even... */
    @Benchmark
    @BenchmarkMode(Mode.All)
    @OutputTimeUnit(TimeUnit.MICROSECONDS)
    public void measureAll() throws InterruptedException {
        TimeUnit.MILLISECONDS.sleep(100);
    }
    /* * ============================== HOW TO RUN THIS TEST: ==================================== * * You are expected to see the different run modes for the same benchmark. * Note the units are different, scores are consistent with each other. * * You can run this test: * * a) Via the command line: * $ mvn clean install * $ java -jar target/benchmarks.jar JMHSample_02 -wi 5 -i 5 -f 1 * (we requested 5 warmup/measurement iterations, single fork) * * b) Via the Java API: * (see the JMH homepage for possible caveats when running from IDE: * http://openjdk.java.net/projects/code-tools/jmh/) */
    public static void main(String[] args) throws RunnerException {
        Options opt = new OptionsBuilder()
                .include(JMHSample_02_BenchmarkModes.class.getSimpleName())
                .warmupIterations(5)
                .measurementIterations(5)
                .forks(1)
                .build();
        new Runner(opt).run();
    }
}

public class JMHSample_03_States { 
   
    @State(Scope.Benchmark)
    public static class BenchmarkState { 
   
        volatile double x = Math.PI;
    }
    @State(Scope.Thread)
    public static class ThreadState { 
   
        volatile double x = Math.PI;
    }
    /* * Benchmark methods can reference the states, and JMH will inject the * appropriate states while calling these methods. You can have no states at * all, or have only one state, or have multiple states referenced. This * makes building multi-threaded benchmark a breeze. * * For this exercise, we have two methods. */
    @Benchmark
    public void measureUnshared(ThreadState state) {
        // All benchmark threads will call in this method.
        //
        // However, since ThreadState is the Scope.Thread, each thread
        // will have it's own copy of the state, and this benchmark
        // will measure unshared case.
        state.x++;
    }
    @Benchmark
    public void measureShared(BenchmarkState state) {
        // All benchmark threads will call in this method.
        //
        // Since BenchmarkState is the Scope.Benchmark, all threads
        // will share the state instance, and we will end up measuring
        // shared case.
        state.x++;
    }

    public static void main(String[] args) throws RunnerException {
        Options opt = new OptionsBuilder()
                .include(JMHSample_03_States.class.getSimpleName())
                .warmupIterations(5)
                .measurementIterations(5)
                .threads(4)
                .forks(1)
                .build();
        new Runner(opt).run();
    }
}

@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.NANOSECONDS)
@Warmup(iterations = 5, time = 1, timeUnit = TimeUnit.SECONDS)
@Measurement(iterations = 5, time = 1, timeUnit = TimeUnit.SECONDS)
@Fork(1)
@State(Scope.Benchmark)
public class JMHSample_27_Params { 
   
    /** * In many cases, the experiments require walking the configuration space * for a benchmark. This is needed for additional control, or investigating * how the workload performance changes with different settings. */
    @Param({
  
  "1", "31", "65", "101", "103"})
    public int arg;
    @Param({
  
  "0", "1", "2", "4", "8", "16", "32"})
    public int certainty;
    @Benchmark
    public boolean bench() {
        return BigInteger.valueOf(arg).isProbablePrime(certainty);
    }
    public static void main(String[] args) throws RunnerException {
        Options opt = new OptionsBuilder()
                .include(JMHSample_27_Params.class.getSimpleName())
// .param("arg", "41", "42") // Use this to selectively constrain/override parameters
                .build();
        new Runner(opt).run();
    }
}

/* * This demonstrates Option A: * * Merge multiple results into one and return it. * This is OK when is computation is relatively heavyweight, and merging * the results does not offset the results much. */
@Benchmark
public double measureRight_1() {
    return Math.log(x1) + Math.log(x2);
}
/* * This demonstrates Option B: * * Use explicit Blackhole objects, and sink the values there. * (Background: Blackhole is just another @State object, bundled with JMH). */
@Benchmark
public void measureRight_2(Blackhole bh) {
    bh.consume(Math.log(x1));
    bh.consume(Math.log(x2));
}

@State(Scope.Thread)
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.NANOSECONDS)
public class JMHSample_10_ConstantFold { 
   
    private double x = Math.PI;
    private final double wrongX = Math.PI;
    @Benchmark
    public double baseline() {
        // simply return the value, this is a baseline
        return Math.PI;
    }
    @Benchmark
    public double measureWrong_1() {
        // This is wrong: the source is predictable, and computation is foldable.
        return Math.log(Math.PI);
    }
    @Benchmark
    public double measureWrong_2() {
        // This is wrong: the source is predictable, and computation is foldable.
        return Math.log(wrongX);
    }
    @Benchmark
    public double measureRight() {
        // This is correct: the source is not predictable.
        return Math.log(x);
    }
    public static void main(String[] args) throws RunnerException {
        Options opt = new OptionsBuilder()
                .include(JMHSample_10_ConstantFold.class.getSimpleName())
                .warmupIterations(5)
                .measurementIterations(5)
                .forks(1)
                .build();
        new Runner(opt).run();
    }
}

for (i = 1; i <= 60; i++) 
   a[i] = a[i] * b + c;

for (i = 1; i <= 60; i+=3)
{
  a[i] = a[i] * b + c;
  a[i+1] = a[i+1] * b + c;
  a[i+2] = a[i+2] * b + c;
}

/* * Suppose we want to measure how much it takes to sum two integers: */
int x = 1;
int y = 2;
/* * This is what you do with JMH. */
@Benchmark
@OperationsPerInvocation(100)
public int measureRight() {
    return (x + y);
}

@State(Scope.Thread)
@Warmup(iterations = 5, time = 1, timeUnit = TimeUnit.SECONDS)
@Measurement(iterations = 5, time = 1, timeUnit = TimeUnit.SECONDS)
@Fork(3)
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.NANOSECONDS)
public class JMHSample_34_SafeLooping { 
   
    /* * JMHSample_11_Loops warns about the dangers of using loops in @Benchmark methods. * Sometimes, however, one needs to traverse through several elements in a dataset. * This is hard to do without loops, and therefore we need to devise a scheme for * safe looping. */
    /* * Suppose we want to measure how much it takes to execute work() with different * arguments. This mimics a frequent use case when multiple instances with the same * implementation, but different data, is measured. */
    static final int BASE = 42;
    static int work(int x) {
        return BASE + x;
    }
    /* * Every benchmark requires control. We do a trivial control for our benchmarks * by checking the benchmark costs are growing linearly with increased task size. * If it doesn't, then something wrong is happening. */
    @Param({
  
  "1", "10", "100", "1000"})
    int size;
    int[] xs;
    @Setup
    public void setup() {
        xs = new int[size];
        for (int c = 0; c < size; c++) {
            xs[c] = c;
        }
    }
    /* * First, the obviously wrong way: "saving" the result into a local variable would not * work. A sufficiently smart compiler will inline work(), and figure out only the last * work() call needs to be evaluated. Indeed, if you run it with varying $size, the score * will stay the same! */
    @Benchmark
    public int measureWrong_1() {
        int acc = 0;
        for (int x : xs) {
            acc = work(x);
        }
        return acc;
    }
    /* * Second, another wrong way: "accumulating" the result into a local variable. While * it would force the computation of each work() method, there are software pipelining * effects in action, that can merge the operations between two otherwise distinct work() * bodies. This will obliterate the benchmark setup. * * In this example, HotSpot does the unrolled loop, merges the $BASE operands into a single * addition to $acc, and then does a bunch of very tight stores of $x-s. The final performance * depends on how much of the loop unrolling happened *and* how much data is available to make * the large strides. */
    @Benchmark
    public int measureWrong_2() {
        int acc = 0;
        for (int x : xs) {
            acc += work(x);
        }
        return acc;
    }
    /* * Now, let's see how to measure these things properly. A very straight-forward way to * break the merging is to sink each result to Blackhole. This will force runtime to compute * every work() call in full. (We would normally like to care about several concurrent work() * computations at once, but the memory effects from Blackhole.consume() prevent those optimization * on most runtimes). */
    @Benchmark
    public void measureRight_1(Blackhole bh) {
        for (int x : xs) {
            bh.consume(work(x));
        }
    }
    /* * DANGEROUS AREA, PLEASE READ THE DESCRIPTION BELOW. * * Sometimes, the cost of sinking the value into a Blackhole is dominating the nano-benchmark score. * In these cases, one may try to do a make-shift "sinker" with non-inlineable method. This trick is * *very* VM-specific, and can only be used if you are verifying the generated code (that's a good * strategy when dealing with nano-benchmarks anyway). * * You SHOULD NOT use this trick in most cases. Apply only where needed. */
    @Benchmark
    public void measureRight_2() {
        for (int x : xs) {
            sink(work(x));
        }
    }
    @CompilerControl(CompilerControl.Mode.DONT_INLINE)
    public static void sink(int v) {
        // IT IS VERY IMPORTANT TO MATCH THE SIGNATURE TO AVOID AUTOBOXING.
        // The method intentionally does nothing.
    }

    public static void main(String[] args) throws RunnerException {
        Options opt = new OptionsBuilder()
                .include(JMHSample_34_SafeLooping.class.getSimpleName())
                .warmupIterations(5)
                .measurementIterations(5)
                .forks(3)
                .build();
        new Runner(opt).run();
    }
}

/*
 * Copyright (c) 2014, Oracle America, Inc.
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 *  * Redistributions of source code must retain the above copyright notice,
 *    this list of conditions and the following disclaimer.
 *
 *  * Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 *  * Neither the name of Oracle nor the names of its contributors may be used
 *    to endorse or promote products derived from this software without
 *    specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
 * THE POSSIBILITY OF SUCH DAMAGE.
 */